SKILLEMALL.ai
RU Sign in

BF openclaw-guardian

Deploy and manage a Guardian watchdog process for OpenClaw Gateway. Provides automated health monitoring, self-repair via `doctor --fix`, git-based workspace rollback, daily snapshots, and optional Discord alerting. Use when a user wants to harden their OpenClaw instance against crashes, config corruption, or bad workspace edits — or when setting up Guardian for the first time on a new server/container.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 540 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Deploy and manage a Guardian watchdog process for OpenClaw Gateway.

As a process F 38/100 · Will not run — References files that are not bundled: scripts/guardian.sh, references/setup.md

ProcedureDiscordSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
97
Quality 40%
71
Run on models
none yet
Process rating
F
38/100
Will not run
References files that are not bundled: scripts/guardian.sh, references/setup.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • low Dangerous commands cmd-background-process SKILL.md:43
    Starts a background / autostarted process (documentation of a security skill)
    nohup ~/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:53
    Starts a background / autostarted process (documentation of a security skill)
    nohup /home/ubuntu/.openclaw/guardian.sh >> /tmp/openclaw-guardian.log 2>&1 &
    security skill
  • low Exfiltration exfil-webhook-url SKILL.md:59
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    export DISCORD_WEBHOOK_URL="https://discord.com/api/webhooks/..."
    placeholder

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/guardian.sh
  • warning missing-ref reference to a missing file: references/setup.md

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: scripts/guardian.sh, references/setup.md
  • 0Tools and files. 2 referenced file(s) missing: scripts/guardian.sh, references/setup.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (openclaw-guardian) differs from the folder (openclaw-guardian-ultra)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 8 steps
  • 100Execution cost. Instruction body is 540 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +3Description length 406: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.